How to install Xaibo with different dependency groups¶
This guide shows you how to install Xaibo with only the dependencies you need for your specific use case.
Prerequisites¶
Before installing Xaibo, ensure you have: - Python 3.10 or higher installed - pip or uv package manager
Install core Xaibo package¶
Install the minimal Xaibo package without optional dependencies:
This gives you the core framework with basic functionality.
Install with specific LLM providers¶
OpenAI models (GPT-3.5, GPT-4)¶
Anthropic Claude models¶
Google Gemini models¶
AWS Bedrock models¶
Multiple LLM providers¶
Install with web server capabilities¶
For running the debug UI and API endpoints:
This includes FastAPI, Strawberry GraphQL, and other web dependencies.
Install with local AI capabilities¶
For local embeddings, tokenization, and transformers:
This includes sentence-transformers, tiktoken, and Hugging Face transformers.
Install everything¶
For full functionality with all optional dependencies:
Install for development¶
If you're contributing to Xaibo or need development tools:
This includes coverage tools and development utilities.
Using uv (recommended)¶
For faster installation and better dependency resolution, use uv
:
Verify installation¶
Test your installation by checking the version:
Or use the CLI:
Quick start after installation¶
Initialize a new project to test your installation:
# Create a new project
uvx xaibo init my_test_project
# Navigate to the project
cd my_test_project
# Start the development server
uv run xaibo dev
Visit http://localhost:9001
to see the debug UI and confirm everything is working.
Troubleshooting¶
Import errors for optional dependencies¶
If you get import errors like ModuleNotFoundError: No module named 'openai'
, install the missing dependency group:
Version conflicts¶
If you encounter dependency conflicts, try using uv which has better dependency resolution:
Virtual environment issues¶
Always install Xaibo in a virtual environment to avoid conflicts: